© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 89155
    Prev
    Next
    INDEX
    Explanations

    mentions of universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atto
    -0.08
    ναν
    -0.08
    olley
    -0.08
     ancor
    -0.08
    emin
    -0.07
    resse
    -0.07
    rif
    -0.07
    çĦ¶
    -0.07
     fitte
    -0.07
    perator
    -0.07
    POSITIVE LOGITS
     of
    0.09
    _of
    0.06
    MBER
    0.06
    _APPEND
    0.06
     Westbrook
    0.06
     Bern
    0.05
    -wide
    0.05
     mug
    0.05
     Hij
    0.05
     consensus
    0.05
    Activations Density 0.009%

    No Known Activations